Jon Shapiro 92697edb7c fix(venice): add compat settings to prevent HTTP 400 errors

Venice's API doesn't support certain OpenAI-compatible parameters that
Clawdbot sends by default:

- `store`: Venice returns HTTP 400 with no body when this is present
- `developer` role: Not supported by Venice's API

This adds VENICE_COMPAT settings (supportsStore: false,
supportsDeveloperRole: false) to all Venice model definitions, both
from the static catalog and dynamically discovered models.

Fixes issues reported in PR #1666 where users experienced silent
failures (HTTP 400, no body) when using Venice models.

Co-authored-by: jonisjongithub <jonisjongithub@users.noreply.github.com>
Co-authored-by: Clawdbot <bot@clawd.bot>

2026-01-26 17:56:01 -08:00

2.5 KiB

Raw Blame History

summary

read_when

JSON-only LLM tasks for workflows (optional plugin tool)

You want a JSON-only LLM step inside workflows

You need schema-validated LLM output for automation

LLM Task

llm-task is an optional plugin tool that runs a JSON-only LLM task and returns structured output (optionally validated against JSON Schema).

This is ideal for workflow engines like Lobster: you can add a single LLM step without writing custom Clawdbot code for each workflow.

Enable the plugin

Enable the plugin:

{
  "plugins": {
    "entries": {
      "llm-task": { "enabled": true }
    }
  }
}

Allowlist the tool (it is registered with optional: true):

{
  "agents": {
    "list": [
      {
        "id": "main",
        "tools": { "allow": ["llm-task"] }
      }
    ]
  }
}

Config (optional)

{
  "plugins": {
    "entries": {
      "llm-task": {
        "enabled": true,
        "config": {
          "defaultProvider": "openai-codex",
          "defaultModel": "gpt-5.2",
          "defaultAuthProfileId": "main",
          "allowedModels": ["openai-codex/gpt-5.2"],
          "maxTokens": 800,
          "timeoutMs": 30000
        }
      }
    }
  }
}

allowedModels is an allowlist of provider/model strings. If set, any request outside the list is rejected.

Tool parameters

prompt (string, required)
input (any, optional)
schema (object, optional JSON Schema)
provider (string, optional)
model (string, optional)
authProfileId (string, optional)
temperature (number, optional)
maxTokens (number, optional)
timeoutMs (number, optional)

Output

Returns details.json containing the parsed JSON (and validates against schema when provided).

Example: Lobster workflow step

clawd.invoke --tool llm-task --action json --args-json '{
  "prompt": "Given the input email, return intent and draft.",
  "input": {
    "subject": "Hello",
    "body": "Can you help?"
  },
  "schema": {
    "type": "object",
    "properties": {
      "intent": { "type": "string" },
      "draft": { "type": "string" }
    },
    "required": ["intent", "draft"],
    "additionalProperties": false
  }
}'

Safety notes

The tool is JSON-only and instructs the model to output only JSON (no code fences, no commentary).
No tools are exposed to the model for this run.
Treat output as untrusted unless you validate with schema.
Put approvals before any side-effecting step (send, post, exec).

2.5 KiB Raw Blame History